English
Related papers

Related papers: Influence-based Attributions can be Manipulated

200 papers

The goal of data attribution is to trace the model's predictions through the learning algorithm and back to its training data. thereby identifying the most influential training samples and understanding how the model's behavior leads to…

Machine Learning · Computer Science 2025-08-12 Hongbo Zhu , Angelo Cangelosi

Diffusion models have led to significant advancements in generative modelling. Yet their widespread adoption poses challenges regarding data attribution and interpretability. In this paper, we aim to help address such challenges in…

Machine Learning · Computer Science 2025-05-27 Bruno Mlodozeniec , Runa Eschenhagen , Juhan Bae , Alexander Immer , David Krueger , Richard Turner

Influence functions are commonly used to attribute model behavior to training documents. We explore the reverse: crafting training data that induces model behavior. Our framework, Infusion, uses scalable influence-function approximations to…

Machine Learning · Computer Science 2026-04-09 J Rosser , Robert Kirk , Edward Grefenstette , Jakob Foerster , Laura Ruis

Influence estimation tools -- such as memorization scores -- are widely used to understand model behavior, attribute training data, and inform dataset curation. However, recent applications in data valuation and responsible machine learning…

Machine Learning · Computer Science 2025-09-30 Tue Do , Varun Chandrasekaran , Daniel Alabi

We consider a crowdsourcing data acquisition scenario, such as federated learning, where a Center collects data points from a set of rational Agents, with the aim of training a model. For linear regression models, we show how a payment…

Machine Learning · Computer Science 2019-09-02 Adam Richardson , Aris Filos-Ratsikas , Boi Faltings

How does the training data affect a model's behavior? This is the question we seek to answer with data attribution. The leading practical approaches to data attribution are based on influence functions (IF). IFs utilize a first-order Taylor…

Machine Learning · Computer Science 2025-09-11 Ittai Rubinstein , Samuel B. Hopkins

Randomness is an unavoidable part of training deep learning models, yet something that traditional training data attribution algorithms fail to rigorously account for. They ignore the fact that, due to stochasticity in the initialisation…

Machine Learning · Computer Science 2025-10-28 Bruno Mlodozeniec , Isaac Reid , Sam Power , David Krueger , Murat Erdogdu , Richard E. Turner , Roger Grosse

Influence functions approximate the effect of training samples in test-time predictions and have a wide variety of applications in machine learning interpretability and uncertainty estimation. A commonly-used (first-order) influence…

Machine Learning · Computer Science 2021-02-12 Samyadeep Basu , Philip Pope , Soheil Feizi

Influence functions (IF) have been seen as a technique for explaining model predictions through the lens of the training data. Their utility is assumed to be in identifying training examples "responsible" for a prediction so that, for…

Machine Learning · Computer Science 2023-05-29 Andrea Schioppa , Katja Filippova , Ivan Titov , Polina Zablotskaia

Machine learning systems such as large scale recommendation systems or natural language processing systems are usually trained on billions of training points and are associated with hundreds of billions or trillions of parameters. Improving…

Machine Learning · Computer Science 2023-05-26 Michael Kounavis , Ousmane Dia , Ilqar Ramazanli

As large language models are increasingly trained and fine-tuned, practitioners need methods to identify which training data drive specific behaviors, particularly unintended ones. Training Data Attribution (TDA) methods address this by…

Influence functions estimate the effect of removing a training point on a model without the need to retrain. They are based on a first-order Taylor approximation that is guaranteed to be accurate for sufficiently small changes to the model,…

Machine Learning · Computer Science 2019-11-22 Pang Wei Koh , Kai-Siang Ang , Hubert H. K. Teo , Percy Liang

Models can expose sensitive information about their training data. In an attribute inference attack, an adversary has partial knowledge of some training records and access to a model trained on those records, and infers the unknown values…

Cryptography and Security · Computer Science 2022-09-07 Bargav Jayaraman , David Evans

A variety of fairness constraints have been proposed in the literature to mitigate group-level statistical bias. Their impacts have been largely evaluated for different groups of populations corresponding to a set of sensitive attributes,…

Machine Learning · Computer Science 2022-07-01 Jialu Wang , Xin Eric Wang , Yang Liu

Influence diagnostics such as influence functions and approximate maximum influence perturbations are popular in machine learning and in AI domain applications. Influence diagnostics are powerful statistical tools to identify influential…

Machine Learning · Statistics 2023-09-21 Jillian Fisher , Lang Liu , Krishna Pillutla , Yejin Choi , Zaid Harchaoui

Transfer learning is a popular method for tuning pretrained (upstream) models for different downstream tasks using limited data and computational resources. We study how an adversary with control over an upstream model used in transfer…

Machine Learning · Computer Science 2023-03-22 Yulong Tian , Fnu Suya , Anshuman Suri , Fengyuan Xu , David Evans

As machine learning is increasingly deployed in the real world, it is paramount that we develop the tools necessary to analyze the decision-making of the models we train and deploy to end-users. Recently, researchers have shown that…

Machine Learning · Computer Science 2022-05-05 Andrew Silva , Rohit Chopra , Matthew Gombolay

Model selection requires repeatedly evaluating models on a given dataset and measuring their relative performances. In modern applications of machine learning, the models being considered are increasingly more expensive to evaluate and the…

Machine Learning · Computer Science 2020-10-21 Anant Raj , Cameron Musco , Lester Mackey , Nicolo Fusi

Good models require good training data. For overparameterized deep models, the causal relationship between training data and model predictions is increasingly opaque and poorly understood. Influence analysis partially demystifies training's…

Machine Learning · Computer Science 2024-04-02 Zayd Hammoudeh , Daniel Lowd

Data attribution seeks to trace model behavior back to the training examples that shaped it, enabling debugging, auditing, and data valuation at scale. Classical influence-function methods offer a principled foundation but remain…

Machine Learning · Computer Science 2025-11-26 Sibo Ma , Julian Nyarko
‹ Prev 1 2 3 10 Next ›